© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87548
    Prev
    Next
    INDEX
    Explanations

    references to permissions and consent related to content use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اÙģع
    -0.08
    klä
    -0.07
    ertools
    -0.07
    ToLeft
    -0.07
    रण
    -0.07
    osemite
    -0.07
    оваÑĢи
    -0.07
    zym
    -0.07
    cak
    -0.07
     pstmt
    -0.07
    POSITIVE LOGITS
    uff
    0.07
     Bran
    0.07
    daf
    0.07
    irt
    0.06
    ourt
    0.06
     fully
    0.06
     paid
    0.06
    an
    0.06
     approval
    0.06
    er
    0.06
    Activations Density 0.001%

    No Known Activations